Zeyi-Lin / Qwen2-VL-finetune-LatexOCR
☆14Updated last month
Alternatives and similar repositories for Qwen2-VL-finetune-LatexOCR:
Users that are interested in Qwen2-VL-finetune-LatexOCR are comparing it to the libraries listed below
- Accelerating GOT-OCRv2 with VLLM☆9Updated 4 months ago
- 研究GOT-OCR-项目落地加速,不限语言☆59Updated 5 months ago
- 卡证和文档检测和矫正☆49Updated 6 months ago
- ☆26Updated 5 months ago
- 中文论文、证券类、财报类PDF数据☆25Updated 9 months ago
- 基于TrOCR + UniMER-1M数据集,训练一个小而美的公式识别模型☆21Updated 4 months ago
- 安卓手机部署DeepSeek-R1 蒸馏的1.5B模型☆19Updated last month
- 基于MNN-llm的安卓手机部署大语言模型:Qwen1.5-0.5B-Chat☆72Updated 11 months ago
- 文档图像处理工具(Document image processing tool),包括漂白 / 文字方向矫正 / 清晰增强 / 笔记去噪美化 / 去阴影 / 扭曲矫正 / 切边增强(DocBleach / TextOrientationCorrection / DocSha…☆44Updated 7 months ago
- 修正文档扭曲/模糊/阴影等情况,使用onnx模型简单轻量部署,未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We wi…☆48Updated 3 months ago
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆16Updated 6 months ago
- ☆56Updated last year
- 在监控画质下实现对校园自行车的重识别,包含REID模型识别,向量数据库检索,UI展示☆9Updated last year
- 用于学习GOT/Qwen/OnnxLLm☆49Updated 5 months ago
- ☆39Updated 5 months ago
- 从零到一实现了一个多模态 大模型,并命名为Reyes(睿视),R:睿,eyes:眼。Reyes的参数量为8B,视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct,Reyes也通过一个两层MLP投影层连…☆10Updated last month
- 视觉信息抽取任务中,使用OCR识别结果规范多模态大模型的回答☆27Updated 3 months ago
- 表格结构识别LGPMA推理☆23Updated 2 years ago
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆52Updated 4 months ago
- ocr,pdf转docx,pdf to docx☆20Updated 2 years ago
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆41Updated last year
- Inference deployment of the llama3☆11Updated 11 months ago
- [AAAI2025 Oral] Predicting the Original Appearance of Damaged Historical Documents☆69Updated last week
- LLM RAG 应用,支持 API 调用,语音交互。☆11Updated 9 months ago
- ☆30Updated 3 weeks ago
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理,可实现 CPU 上毫秒级的 OCR 精准预测,通用场景中英文OCR达到开源SO…☆65Updated 2 months ago
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆54Updated 6 months ago
- 轻量模型的图像分析web服务,包括倾斜矫正OCR,公章(印章)检测+识别,车牌识别。api方案使用FastAPI+Gunicorn,提供gradio展示。☆89Updated 11 months ago
- ✅Deploy PaddleOCR with flask | 利用Flask对PaddleOCR进行部署,方便调用☆40Updated 2 years ago
- Pytorch DDP Traning Demo☆20Updated 5 months ago